The goal of this work is to perform transfer learning among numerous tasks and to discover visual relationships among them. Specifically, while we intiutively might guess the depth of an image and surface normals are related, this work takes a step forward and discovers a beneficial relationship among 26 tasks in terms of task transferability - many of them are not obvious. This is important for scenarios when an insufficient budget is available for target task for annotation, thus, learned representation from the 'cheaper' task could be used along with small dataset for the target task to reach sufficient performance on par with fully supervised training on a large dataset.

The basis of the approach is to compute an affinity matrix among tasks based on whether the solution for one task can be sufficiently easily used for another task. This approach does not impose human intuition about the task relationships and chooses task transferability based on the quality of a transfer operation in a fully computational manner.

The task taxonomy (i.e. **taskonomy**) is a computationally found directed hypergraph that captures the notion of task transferability over any given task dictionary. It performed using a four-step process depicted in the figure below: ![Process overview. The steps involved in creating the taxonomy.](http://taskonomy.stanford.edu/img/svg/Process.svg)

-  In stage I (**Task-specific Modelling**), a task-specific network is trained in a fully supervised manner. The network is composed of the encoder (modified ResNet-50), and fully convolutional decoder for pixel-to-pixel tasks, or 2-3 FC layers for low-dimensional tasks. Dataset consists of 4 million images of indoor scenes from about 600 buildings; every image has an annotation for every task.

- In stage II (**Transfer modeling**), all feasible transfers between sources and targets are trained (multiple inputs task to single target transfer is also considered). Specifically, after the task-specific networks are trained in stage I, the weights of an encoder are fixed (frozen network is used to extract representations only) and the representation from the encoder is used to train a small readout network (similar to a decoder from stage I) with a new task as a target (i.e. ground truth is available). In total, about 3000 transfer possibilities are trained.

- In stage III (**Taxonomy solver**), the task affinities acquired from the transfer functions performance are normalized. This is needed because different tasks lie in different spaces and transfer function scale. This is performed using ordinal normalization - Analytical Hierarchy Process (details are in the paper - Section 3.3). This results in an affinity matrix where a complete graph of relationships is completely normalized and this graph quantifies a pair-wise set of tasks evaluated in terms of a transfer function (i.e. task dependency).

- In stage IV (**Computed Taxonomy**), a hypergraph which can predict the performance of any transfer policy and optimize for the optimal one is synthesized. This is solved using Binary Integer Program as a subgraph selection problem where tasks are nodes and transfers are edges. After the optimization process, the solution devices a connectivity that solves all target tasks, maximizes their collective performance while using only available source tasks under user-specified constraints (e.g. budget).

So, if you want to train your network on an unseen task, you can obtain pretrained weights for existing tasks from the [project page](https://github.com/StanfordVL/taskonomy/tree/master/taskbank), train readout functions against each task (as well as combination of multiple inputs), build an affinity matrix to know where your task is positioned against the other ones, and through subgraph selection procedure observe what tasks have favourable influence on your task. Consequently, you can train your task with much less data by utilizing representations from the existing tasks which share visual significance with your task. Magnificent!

Through a likelihood-focused derivation of a variational inference (VI) loss, Variational Generative Experience Replay (VGER) presents the closest appropriate likelihood- focused alternative to Variational Continual Learning (VCL), the state-of the art prior-focused approach to continual learning.


In non continual learning, the aim is to learn parameters $\omega$ using labelled training data $\mathcal{D}$ to infer $p(y|\omega, x)$. In the continual learning context, instead, the data is not independently and identically distributed (i.i.d.), but may be split into separate tasks $\mathcal{D}_t = (X_t, Y_t)$ whose examples $x_t^{n_t}$ and $y_t^{n_t}$ are assumed to be i.i.d. 


In \cite{Farquhar18}, as the loss at time $t$ cannot be estimated for previously discarded datasets, to approximate the distribution of past datasets $p_t(x,y)$, VGER (Variational Generative Experience Replay) trains a GAN $q_t(x, y)$ to produce ($\hat{x}, \hat{y}$) pairs for each class in each dataset as it arrives (generator is kept while data is discarded after each dataset is used). The variational free energy $\mathcal{F}_T$ is used to train on dataset $\mathcal{D}_T$ augmented with samples generated by the GAN. In this way the prior is set as the posterior approximation from the previous task.

_Disclaimer: I'm the first author of this paper._

The code for this paper can be found at https://github.com/fabioperez/skin-data-augmentation.

In this work, we wanted to compare different data augmentation scenarios for skin lesion analysis. We tried 13 scenarios, including commonly used augmentation techniques (color and geometry transformations), unusual ones (random erasing, elastic transformation, and a novel lesion mix to simulate collision lesions), and a combination of those. 

Examples of the augmentation scenarios:

https://i.imgur.com/TpgxzLZ.png

a) no augmentation

b) color (saturation, contrast, and brightness)

c) color (saturation, contrast, brightness, and hue)

d) affine (rotation, shear, scaling)

e) random flips

f) random crops

g) random erasing

h) elastic

i) lesion mix

j) basic set (f, d, e, c)

k) basic set + erasing (f, g, d, e, c)

l) basic set + elastic (f, d, h, e, c)

m) basic set + mix (i, f, d, e, c)

---

We used the ISIC 2017 Challenge dataset (2000 training images, 150 validation images, and 600 test images).

We tried three network architectures: Inception-v4, ResNet-152, and DenseNet-161.

We also compared different test-time data augmentation methods: a) no augmentation; b) 144-crops; c) same data augmentation as training (64 augmented copies of the original image). Final prediction was the average of all augmented predictions.


## Results

https://i.imgur.com/WK5VKUf.png

* Basic set (combination of commonly used augmentations) is the best scenario.
* Data augmentation at test-time is very beneficial.
* Elastic is better than no augmentation, but when compared incorporated to the basic set, decreases the performance.
* The best result was better than the winner of the challenge in 2017, without using ensembling.
* Test data augmentation is very similar with 144-crop, but takes less images during prediction (64 vs 144), so it's faster.

# Impact of data augmentation on dataset sizes

We also used the basic set scenarios on different dataset sizes by sampling random subsets of the original dataset, with sizes 1500, 1000, 500, 250 and 125.

https://i.imgur.com/m3Ut6ht.png

## Results

* Using data augmentation can be better than using more data (but you should always use more data since the model can benefit from both). For instance, using 500 images with data augmentation on training and test for Inception is better than training with no data augmentation with 2000 images.
* ResNet and DenseNet works better than Inception for less data.
* Test-time data augmentation is always better than not augmenting on test-time.
* Using data augmentation on train only was worse than not augmenting at all in some cases.

This paper posits that one of the central problems stopping multi-task RL - that is, single models trained to perform multiple tasks well - from reaching better performance, is the inability to balance model resources and capacity between the different tasks the model is being asked to learn. Empirically, prior to this paper, multi-task RL could reach ~50% of human accuracy on Atari and Deepmind Lab tasks. The fact that this is lower than human accuracy is actually somewhat less salient than the fact that it’s quite a lot lower than single-task RL - how a single model trained to perform only that task could do. 

When learning a RL model across multiple tasks, the reward structures of the different tasks can vary dramatically. Some can have high-magnitude, sparse rewards, some can have low magnitude rewards throughout. If a model learns it can gain what it thinks is legitimately more reward by getting better at a game with an average reward of 2500 than it does with an average reward of 15, it will put more capacity into solving the former task. Even if you apply normalization strategies like reward clipping (which treats all rewards as a binary signal, regardless of magnitude, and just seeks to increase the frequency of rewards), that doesn’t deal with some environments having more frequent rewards than others, and thus more total reward when summed over timestep. 


The authors here try to solve this problem by performing a specific kind of normalization, called Pop Art normalization, on the problem. PopArt normalization (don’t worry about the name) works by adaptively normalizing both the target and the estimate of the target output by the model, at every step. In the Actor-Critic case that this model is working on, the target and estimate that are being normalized are, respectively, 1) the aggregated rewards of the trajectories from state S onward, and 2) the value estimate at state S. If your value function is perfect, these two things should be equivalent, and so you optimize your value function to be closer to the true rewards under your policy. And, then, you update your policy to increase probability of actions with higher advantage (expected reward with that action, relative to the baseline Value(S) of that state).  The “adaptive” part of that refers to correcting for the fact when you’re estimating, say, a Value function to predict the total future reward of following a policy at a state, that V(S) will be strongly non-stationary, since by improving your policy you are directly optimizing to increase that value. This is done by calculating “scale” and “shift” parameters off of a recent data. 

The other part of the PopArt algorithm works by actually updating the estimate our model is producing, to stay normalized alongside the continually-being-re-normalized target. 

https://i.imgur.com/FedXTfB.png
It does this by taking the new and old versions of scale (sigma) and shift (mu) parameters (which will be used to normalize the target) and updates the weights and biases of the last layer, such that the movement of the estimator moves along with the movement in the target. 

Using this toolkit, this paper proposes learning one *policy* that’s shared over all task, but keeping shared value estimation functions for each task. Then, it normalizes each task’s values independently, meaning that each task ends up contributing equal weight to the gradient updates of the model (both for the Value and Policy updates). In doing this, the authors find dramatically improved performance at both Atari and Deepmind, relative to prior IMPALA work
https://i.imgur.com/nnDcjNm.png
https://i.imgur.com/Z6JClo3.png

### Summary
Knowing when a model is qualified to make a prediction is critical to safe deployment of ML technology. Model-independent / Unsupervised Out-of-Distribution (OoD) detection is appealing mostly because it doesn't require task-specific labels to train. It is tempting to suggest a simple one-tailed test in which lower likelihoods are OoD (assigned by a Likelihood Model), but the intuition that In-Distribution (ID) inputs should have highest likelihoods _does not hold in higher dimension_. The authors propose to use the Watanabe-Akaike Information Criterion (WAIC) to circumvent this problem and empirically show the robustness of the approach.

### Counterintuitive Properties of Likelihood Models:
https://i.imgur.com/4vo0Ff5.png
So a GLOW model with Gaussian prior maps SVHN closer to the origin than Cifar (but never actually generates SVHN because Gaussian samples are on the shell). This is bad news for OoD detection.

### Proposed Methodology:
Use the WAIC criterion for OoD detection which gives an asymptotically correct estimate of the gap between the training set and test set expectations:
https://i.imgur.com/vasSxuk.png
Basically,  the correction term subtracts the variance in likelihoods across independent samples from the posterior. This acts to robustify the estimate, ensuring that points that are sensitive to the particular choice of posterior are penalized. They use an ensemble of generative models as a proxy for posterior samples i.e. the ensembles acts as approximate posterior samples.
Now, OoD can be detected with a Likelihood Model:
https://i.imgur.com/M3CDKOA.png
### Discussion
Interestingly, GLOW maps Cifar and other datasets INSIDE the gaussian shell (which is an annulus of radius $\sqrt{dim} = \sqrt{3072} \approx 55.4$
https://i.imgur.com/ERdgOaz.png
This is in itself quite disturbing, as it suggests that better flow-based generative models (for sampling) can be obtained by encouraging the training distribution to overlap better with the typical set in latent
space.